RGCNRepresentations

class RGCNRepresentations(triples_factory, embedding_specification, num_layers=2, use_bias=True, activation=None, activation_kwargs=None, edge_dropout=0.4, self_loop_dropout=0.2, edge_weighting=None, decomposition=None, decomposition_kwargs=None, regularizer=None, regularizer_kwargs=None)

Bases: pykeen.nn.emb.RepresentationModule

Entity representations enriched by R-GCN.

The GCN employed by the entity encoder is adapted to include typed edges. The forward pass of the GCN is defined by:

\[\textbf{e}_{i}^{l+1} = \sigma \left( \sum_{r \in \mathcal{R}}\sum_{j\in \mathcal{N}_{i}^{r}} \frac{1}{c_{i,r}} \textbf{W}_{r}^{l} \textbf{e}_{j}^{l} + \textbf{W}_{0}^{l} \textbf{e}_{i}^{l}\right)\]

where \(\mathcal{N}_{i}^{r}\) is the set of neighbors of node \(i\) that are connected to \(i\) by relation \(r\), \(c_{i,r}\) is a fixed normalization constant (but it can also be introduced as an additional parameter), and \(\textbf{W}_{r}^{l} \in \mathbb{R}^{d^{(l)} \times d^{(l)}}\) and \(\textbf{W}_{0}^{l} \in \mathbb{R}^{d^{(l)} \times d^{(l)}}\) are weight matrices of the l-th layer of the R-GCN.

The encoder aggregates for each node \(e_i\) the latent representations of its neighbors and its own latent representation \(e_{i}^{l}\) into a new latent representation \(e_{i}^{l+1}\). In contrast to standard GCN, R-GCN defines relation specific transformations \(\textbf{W}_{r}^{l}\) which depend on the type and direction of an edge.

Since having one matrix for each relation introduces a large number of additional parameters, the authors instead propose to use a decomposition, cf. pykeen.nn.message_passing.Decomposition.

Instantiate the R-GCN encoder.

Parameters

• triples_factory (CoreTriplesFactory) – The triples factory holding the training triples used for message passing.

• embedding_specification (EmbeddingSpecification) – The base embedding specification.

• num_layers (int) – The number of layers.

• use_bias (bool) – Whether to use a bias.

• activation (Union[str, Module, None]) – The activation.

• activation_kwargs (Optional[Mapping[str, Any]]) – Additional keyword based arguments passed if the activation is not pre-instantiated. Ignored otherwise.

• edge_dropout (float) – The edge dropout to use. Does not apply to self-loops.

• self_loop_dropout (float) – The self-loop dropout to use.

• edge_weighting (Union[str, EdgeWeighting, None]) – The edge weighting mechanism.

• decomposition (Union[str, Decomposition, None]) – The decomposition, cf. pykeen.nn.message_passing.Decomposition.

• decomposition_kwargs (Optional[Mapping[str, Any]]) – Additional keyword based arguments passed to the decomposition upon instantiation.

• regularizer (Union[str, Regularizer, None]) – A regularizer, which is applied to the selected embeddings in forward pass

• regularizer_kwargs (Optional[Mapping[str, Any]]) – Additional keyword arguments passed to the regularizer

Methods Summary

forward([indices])	Enrich the entity embeddings of the decoder using R-GCN message propagation.
post_parameter_update()	Apply constraints which should not be included in gradients.
reset_parameters()	Reset the module's parameters.

Methods Documentation

forward(indices=None)

Enrich the entity embeddings of the decoder using R-GCN message propagation.

Return type

FloatTensor

post_parameter_update()

Apply constraints which should not be included in gradients.

Return type

None

reset_parameters()

Reset the module’s parameters.